AEGIS is a novel system that significantly improves the scalability of running large, long-sequence Transformer models under Fully Homomorphic Encryption (FHE) on multi-GPU systems by optimizing data…

This paper provides a comprehensive, system-level comparison of MPC and FHE for Privacy-Preserving Machine Learning (PPML) across various models and environments, moving beyond single-metric latency a…

The paper proposes a co-design paradigm, 'Meeting in the Middle,' to make Fully Homomorphic Encryption (FHE) practical for AI inference by optimizing both the cryptographic schemes and the underlying…

This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…

This paper demonstrates a novel attack against the shuffling defense used in secure Transformer inference, showing that randomly permuted activations can still be exploited to recover model weights.

SecureRouter is an encrypted routing and inference framework that accelerates secure transformer inference by adaptively selecting the optimal model size based on the encrypted input, achieving a 1.95…

This paper provides a comparative analysis and benchmarking of Secure Multi-Party Computation (SMPC) and Fully Homomorphic Encryption (FHE) for machine learning, finding that the optimal choice depend…

The paper proposes a Public/Private Hybrid Head-VFL (PPHH-VFL) architecture that significantly accelerates secure time-series inference by splitting the model head into efficient public and secure pri…

The paper introduces public-decay Homomorphic State Space Models (HSSMs) that enable efficient, high-accuracy sequence inference directly on encrypted data, significantly outperforming existing encryp…

This paper evaluates the vulnerability of Fully Homomorphic Encryption (FHE) computation to silent data corruption (SDC) using large-scale fault-injection experiments and theoretical analysis.

The paper introduces TIGER, a GPU-accelerated framework that significantly speeds up high-precision evaluation of nonlinear layers for encrypted LLM inference using TFHE.

The paper addresses the vulnerability of CKKS-based Fully Homomorphic Encryption (FHE) to overflow attacks by proposing a formal verification technique that guarantees certified bounds on all neuron r…

NANOZK introduces a novel, highly efficient zero-knowledge proof system that allows users to cryptographically verify that the output of a large language model (LLM) was generated by a specific, claim…

This paper enhances Federated Learning privacy by integrating two key protection mechanisms—masking and RSA encapsulation—into Hybrid Homomorphic Encryption (HHE) to secure against malicious clients.

The paper proposes $HE^2$, a novel communication-light heterogeneous accelerator architecture that significantly improves the efficiency of Fully Homomorphic Encryption (FHE) by optimizing dataflow an…

The paper proposes $HE^2$, a novel communication-light heterogeneous accelerator architecture that significantly improves the efficiency of Fully Homomorphic Encryption (FHE) by optimizing dataflow an…

The paper proposes Independent Vector Evaluation (IVE), a novel method that significantly reduces the computational cost of generating selection vectors for private embedding lookups under Fully Homom…

This paper demonstrates that the Euston secure inference framework, which uses SVD-based matrix transmission to save bandwidth, leaks private input data by exploiting subspace leakage of random masks.

The paper characterizes Homomorphic Encryption (HE) operations on a real-world Processing-In-Memory (PIM) system, demonstrating that while PIM is a viable alternative to CPUs/GPUs, performance is limi…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…